Update display_cell_tokenize

Author: wannaphong

pythainlp/tokenize/core.py

@@ -757,6 +757,7 @@ def display_cell_tokenize(text: str) -> List[str]:
 
     display_cells = []
     current_cell = ""
+    text = text.replace("ำ", "ํา")
 
     for char in text:
         if re.match(r"[\u0E31\u0E34-\u0E3A\u0E47-\u0E4E]", char):

tests/core/test_tokenize.py

@@ -608,7 +608,10 @@ def test_tcc_p(self):
 
     def test_display_cell_tokenize(self):
         self.assertEqual(display_cell_tokenize(""), [])
-        self.assertEqual(display_cell_tokenize("แม่น้ำอยู่ที่ไหน"), ["แ", "ม่", "น้ํ", "า", "อ", "ยู่", "ที่", "ไ", "ห", "น"])
-        self.assertEqual(display_cell_tokenize("สวัสดี"), ["ส", "ว", "ั", "ส", "ด", "ี"])
+        self.assertEqual(
+            display_cell_tokenize("แม่น้ำอยู่ที่ไหน"),
+            ["แ", "ม่", "น้ํ", "า", "อ", "ยู่", "ที่", "ไ", "ห", "น"]
+        )
+        self.assertEqual(display_cell_tokenize("สวัสดี"), ['ส', 'วั', 'ส', 'ดี'])
         self.assertEqual(display_cell_tokenize("ทดสอบ"), ["ท", "ด", "ส", "อ", "บ"])
         self.assertEqual(display_cell_tokenize("ภาษาไทย"), ["ภ", "า", "ษ", "า", "ไ", "ท", "ย"])